FlatTrack: Eye-tracking with ultra-thin lensless cameras

2025-01-26

AI Summary

To address the bulkiness of conventional lens-based eye-tracking systems in AR/VR glasses, this paper proposes an ultra-thin, lensless planar eye-tracking system. Methodologically, it introduces a novel co-design paradigm integrating near-eye lensless imaging with a gaze regression network, incorporating mask-encoded optical sensing, a lightweight CNN-based regressor, a near-eye synchronized calibration framework, and end-to-end real-time inference optimization. The key contributions include overcoming the optical focusing distance constraint to achieve the world’s thinnest wearable eye tracker: total thickness < 3 mm and weight < 5 g. The system attains commercial-grade accuracy—mean angular error < 1.5°—in both real-world and simulated environments, while supporting real-time tracking at >125 fps.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Existing eye trackers use cameras based on thick compound optical elements, necessitating the cameras to be placed at focusing distance from the eyes. This results in the overall bulk of wearable eye trackers, especially for augmented and virtual reality (AR/VR) headsets. We overcome this limitation by building a compact flat eye gaze tracker using mask-based lensless cameras. These cameras, in combination with co-designed lightweight deep neural network algorithm, can be placed in extreme close proximity to the eye, within the eyeglasses frame, resulting in ultra-flat and lightweight eye gaze tracker system. We collect a large dataset of near-eye lensless camera measurements along with their calibrated gaze directions for training the gaze tracking network. Through real and simulation experiments, we show that the proposed gaze tracking system performs on par with conventional lens-based trackers while maintaining a significantly flatter and more compact form-factor. Moreover, our gaze regressor boasts real-time (>125 fps) performance for gaze tracking.

Problem

• Lightweight
• Lens-free
• Eye-tracking Technology

Innovation

• Lensless Camera
• Eye Tracking
• High-speed Tracking